© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11248
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to longer, multi-syllable, content-heavy words—often technical or specialized terms (e.g. “dramaturgy,” “mnemonically,” “interlinkages”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    T
    0.99
    V
    0.96
    M
    0.93
    v
    0.93
    it
    0.92
    u
    0.88
    l
    0.87
    k
    0.87
    w
    0.86
    N
    0.86
    POSITIVE LOGITS
     层
    0.77
    idenav
    0.71
    ்கள்
    0.69
    ային
    0.66
     Mặt
    0.66
    銑
    0.66
     Сколько
    0.66
     佐
    0.66
     FontSize
    0.65
     说明
    0.63
    Activations Density 1.376%

    No Known Activations